Tag Archives: Zitao

Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction

Posted on December 2, 2023 by | Comments Off on Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction

Zitao Chen and Karthik Pattabiraman, Proceedings of the Network and Distributed Systems Security Conference (NDSS), 2024. (Acceptance Rate: 15%). [ PDF | Talk ] (ArXIV, Code). Artifacts Available, Functional and Reproduced
Continue reading →

Comments Off on Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction

Posted in papers

Tagged , , , ,

Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks

Posted on November 23, 2022 by | Comments Off on Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks

Zitao Chen, Pritam Dash, and Karthik Pattabiraman. Proceedings of the 18th ACM ASIA Conference on Computer and Communications Security (ACM ASIACCS), 2023. (Acceptance Rate: 16%) [ PDF | Talk ] (code)
Continue reading →

Comments Off on Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks

Posted in papers

Tagged , , , , ,

Fault Injection for TensorFlow Applications

Posted on May 10, 2022 by | Comments Off on Fault Injection for TensorFlow Applications

Niranjhana Narayanan, Zitao Chen, Bo Fang, Guanpeng Li, Karthik Pattabiraman, and Nathan DeBardeleben, IEEE Transactions on Dependable and Secure Computing (TDSC). Acceptance Date: May 2022. [ PDF ] (code1, code2)
Continue reading →

Comments Off on Fault Injection for TensorFlow Applications

Posted in papers

Tagged , , , , , , , ,

PID-Piper: Recovering Robotic Vehicles from Physical Attacks

Posted on March 10, 2021 by | Comments Off on PID-Piper: Recovering Robotic Vehicles from Physical Attacks

Pritam Dash, Guanpeng Li, Zitao Chen, Mehdi Karimibiuki, and Karthik Pattabiraman, IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2021. (Acceptance Rate: 16.5%). [ PDF | Talk, Talk Video ] (Code, PID-Piper Videos) Best Paper Award (1 of nearly 300 submissions).
Continue reading →

Comments Off on PID-Piper: Recovering Robotic Vehicles from Physical Attacks

Posted in papers

Tagged , , , , , , , , ,

A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction

Posted on March 10, 2021 by | Comments Off on A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction

Zitao Chen, Guanpeng Li, and Karthik Pattabiraman, IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2021. (Acceptance Rate: 16.5%). [ PDF | Talk , Video] (arXIV, code) Best Paper Award Runner up (1 of 2 among nearly 300 submissions). Incorporated into Intel’s OpenVino2 Framework (More details, Documentation).
Continue reading →

Comments Off on A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction

Posted in papers

Tagged , , , , , , , ,

TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications

Posted on August 14, 2020 by | Comments Off on TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications

Zitao Chen, Niranjhana Narayanan, Bo Fang, Guanpeng Li, Karthik Pattabiraman, and Nathan DeBardeleben, IEEE International Symposium on Software Reliability Engineering (ISSRE), 2020. (Acceptance Rate: 26%) [ PDF | Talk ] (Code)
Continue reading →

Comments Off on TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications

Posted in papers

Tagged , , , , , , , ,

BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems

Posted on June 16, 2019 by | Comments Off on BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems

Zitao Chen, Guanpeng Li, Karthik Pattabiraman, and Nathan DeBardeleben, The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC), 2019. (Acceptance Rate: 21%) [ PDF | Talk ] ( Code Finalist for the SC reproducibility challenge (one of 3 papers))
Continue reading →

Comments Off on BinFI: An Efficient Fault Injector for Safety-Critical Machine Learning Systems

Posted in papers

Tagged , , , , , ,